INDEX

Explanations

phrases related to political discussions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a sense of negativity or hardship

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 metic

-0.68

 Vector

-0.59

omorphic

-0.58

oun

-0.57

Owl

-0.56

 mosqu

-0.56

 citiz

-0.56

 blanket

-0.54

ected

-0.54

 Frontier

-0.54

POSITIVE LOGITS

1.85

ses

1.41

sb

1.20

sat

1.08

sg

1.04

sets

1.04

si

1.04

itates

1.03

ski

1.02

ends

1.02

Activations Density 0.160%

phrases related to political discussions

phrases indicating a sense of negativity or hardship

No Comments

No Known Activations